This repo contains the solutions to the projects of the 2018 summer session of Berkeley's CS188 Introduction to Artificial Intelligence. These projects involve implementing foundational AI techniques to the game of Pac-Man such as informed state-space search, probabilistic inference, and reinforcement learning. The Pac-Man game graphics allow the user to visualize the results of the techniques implemented.
The following items should be installed in your system:
- Python 2.7
- git command line tool
In the table below, you will find a short description of all the projects included in this repo. Each project has a link with the specific project's instructions and questions. The links provided are not for the Summer 2018 version of the course since the links for that course are not available, however the instructions for Fall 2018 version of the course are the same for all projects.
| Project name | Topic | Link to Project Instructions |
|---|---|---|
| P1 - Search | Students implement depth-first, breadth-first, uniform cost, and A* search algorithms. These algorithms are used to solve navigation and traveling salesman problems in the Pacman world. |
Instructions for Project 1 |
| P2 - Multi-Agent Search | Students will apply the search algorithms and problems implemented in Project 1 to handle more difficult scenarios that include controlling multiple pacman agents and planning under time constraints" |
Instructions for Project 2 |
| P3 - Reinforcement Learning | Students implement model-based and model-free reinforcement learning algorithms, applied to the AIMA textbook's Gridworld, Pacman, and a simulated crawling robot. |
Instructions for Project 3 |
| P4 - GhostBusters | Probabilistic inference in a hidden Markov model tracks the movement of hidden ghosts in the Pacman world. Students implement exact inference using the forward algorithm and approximate inference via particle filters. |
Instructions for Project 4 |